DATA COLLECTION IDENTIFYING VARIABLES WHERE TO SOURCE YOUR VARIABLES 9/2/17

Question 1

What are the 3 steps to data collection? (3)

Answer 1

1. decide which variables you might need to collect
2. decide where to source your variables
3. choose between different sources of the same variables

Question 2

What are prospective studies?

Answer 2

record variables over the study period with the outcome measured subsequently

e.g. cohort studies

Question 3

What are retrospective studies?

Answer 3

they measure the outcome and then look backwards to measure the exposure and other variables

e.g. patient records = case control studies

cross-sectional studies

Question 4

What are the pros and cons of prospective data collection? (3,4)

Answer 4

PROS

• Fewer source of bias
• less chance of confounding
• some data can only be measured prospectively

CONS

• time and resource intensive
• tendancy to collect data on more variables than you need or can use in your analysis
• subjects cans drop bias
• unfeasible for rare outcomes

Question 5

What are the pros and cons for retrospective data collection (2,3)

Answer 5

PROS

• data collection is less time and resource intensive
• allows oversampling of rare outcomes

CONS

• more suscpetible to bias
• some variables cannot be measured directly
  e. g. BMI, bp
• little control of data from records

Question 6

What are the pros and cons of newly collected data? (1,4)

Answer 6

PROS

• ensures that you record all the variables you need using the best techniques available applied consistently

CONS

• ethics
• harder to recruit
• expensive
• time consuming

Question 7

What are the pros and cons of existing data? (3)

Answer 7

CONS

• limited choice to which variables have been measured
• limited involvement in the (in)consistency of measurement
• limited involvement in the level of missingness tolerated

Question 8

What does thinking conceptually mean?

Answer 8

the variables you would like to source

• theoretical

Question 9

What does thinking operationally mean?

Answer 9

measuring the variables you want

• practical

Question 10

How do you standardise data collection? (2)

Answer 10

1. research diary
2. data collection pro forma
   - ensures that variables are measured/recorded consistently
   e. g. questionnaires for measurements or participant derived info

Question 11

What are examples of open ended formatting approaches in questionnaires?

Answer 11

• entirely respondent determined

- need coding prior to quantitative analysis

Question 12

What are examples of close-ended formatting approaches in questionnaires? (5)

Answer 12

1. part respondent
2. continuous
3. categorical
4. likert - strongly agree/disagree
5. visual analogue - scale good——x——bad
   - may need coding prior to analysis